Title :
SDTs: sparse dynamic trees
Author :
Adams, Nicholas J. ; Williams, Christopher K I
Author_Institution :
Inst. for Adaptive & Neural Computation, Edinburgh Univ., UK
Abstract :
We introduce a class of image models which we call sparse dynamic trees (SDTs). These extend our previous work (1999) on dynamic trees by introducing a top-down generative prior for the tree structures, which leads to a sparse use of nodes in the network. We present results showing the properties of these networks in action on 1D patterns
Keywords :
neural nets; image models; image segmentation; probability; simulated annealing; sparse dynamic trees; tree structured belief net; tree structures;
Conference_Titel :
Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
Conference_Location :
Edinburgh
Print_ISBN :
0-85296-721-7
DOI :
10.1049/cp:19991163
